Superpixel Based Segmentation and Classification of Polyps in Wireless Capsule Endoscopy

TL;DR

This paper proposes a superpixel-based segmentation and classification method using SLIC and SVM to detect polyps in wireless capsule endoscopy frames, achieving high sensitivity and aiding early diagnosis.

Contribution

It introduces a novel application of SLIC superpixels combined with SVM for polyp detection in WCE images, improving detection sensitivity over previous methods.

Findings

Sensitivity of 91% in polyp classification

Optimal superpixel number improves detection accuracy

Superpixel segmentation enhances prior approaches

Abstract

Wireless Capsule Endoscopy (WCE) is a relatively new technology to record the entire GI trace, in vivo. The large amounts of frames captured during an examination cause difficulties for physicians to review all these frames. The need for reducing the reviewing time using some intelligent methods has been a challenge. Polyps are considered as growing tissues on the surface of intestinal tract not inside of an organ. Most polyps are not cancerous, but if one becomes larger than a centimeter, it can turn into cancer by great chance. The WCE frames provide the early stage possibility for detection of polyps. Here, the application of simple linear iterative clustering (SLIC) superpixel for segmentation of polyps in WCE frames is evaluated. Different SLIC superpixel numbers are examined to find the highest sensitivity for detection of polyps. The SLIC superpixel segmentation is promising to improve the results of previous studies. Finally, the superpixels were classified using a support vector machine (SVM) by extracting some texture and color features. The classification results showed a sensitivity of 91%.